The main loop may now move down to a cheaper model by default
(mainModelSwitch true, fail-closed picker). Both caps measure the COLD
READ a switch costs: the context minus what the target model's prompt
cache already holds, from a per-model served record written on every
main step (1 h TTL, cleared by /clear and /route reload; a smaller
context than the record counts as cold). downgradeMaxTokens defaults to
120000, upgradeMaxTokens keeps 200000; no return bypass is needed since
a warm return is cheap by construction.
The prompt classifier writes the full phase route: coding and
bookkeeping guesses move main down under the switch and the cap; a guess
never ranks above the session model; a mid-turn ultrathink floor keeps
its model; a user /effort typed between turns drops the guess for that
turn only (engine baseline is now per turn). A model-loaded helper skill
inside a best-tier run moves effort only. Main routed onto a model whose
window the context outgrew returns to the session model. The skip line
is said once per cap crossing; the toast names a cap hold; the status
line shows the switch only when off.
rules/default-language.md loads always-on (CLAUDE.global.md at 317/320,
BDR-085 exception path). Interviewer proposes Rust when the language is
not stated; init-project captures the language choice as a founding BDR.
code-clean B5 (enable_tool split into enable_gstack/
enable_external_single/enable_pack), B7 (enable_skill into
enable_gstack_skill/enable_linked_skill/enable_plugin_skill), B9
(cmd_show into _show_entries/_show_plain/_show_grouped, `_show_plain`
ends with an explicit return 0), B18 (locals), B19 (comment).
/refactor C4: tool_kind/tool_source replace the 3 hand-copied name
lists with the MANAGED_TOOLS roster (exact-match loop), and disable_* is
split to mirror enable_*.
/refactor C5: gstack_skills/gstack_parked_names/gstack_park/
gstack_unpark move into lib/gstack-removed.sh, the only sourced file the
fixture suites copy, and profile.sh and toggle-external.sh both use
them.
496-run golden capture identical; make test 47 green, shellcheck 0.
usage() printed lines 3-26 with a hardcoded range, but the tool list
runs to line 32, so 8 of the 14 tools were missing. It now reads
`sed -n '3,/^# ====/p' | sed '$d'` and stops at the closing banner, with
no line numbers. Logged in .claude/audits/BUGS-FOUND.md.
A1 drop unused `import gzip`; B1/B2 file-level shellcheck directives
placed before `set -u`; B3 `cd "$REPO" || exit 1`; B4 hook regex split
into `pattern+=` lines (sha256 of $pattern unchanged); B11
`_build_parser`/`_dispatch` pulled out of google_seo `_cli`; B20
detect-plugins header names update-all.sh; C2 prune-memory deterministic
suite wired into SUITES (literal path); C3 `_refuse_outside_allowlist`
moved up in deploy-commit.
No behavior change except B3 (a failed cd now exits 1) and C2 (one more
suite). B5/B7/B9/B18/B19 land in the refactor commit.
Kill switch fails closed: a present-but-unreadable override at first load
or a non-boolean enabled turns the router off (logged); /route reload says
when the previous config was kept. Prompt rules with nested quantifiers
are dropped; a config path that is not a regular file reads as failed;
caught errors log kind + code only (errWord); rejected keys are masked in
logs (keyWord), alias keys match KEY_NAME, prototype names are never keys;
offers capped at 256; a models alias without a fallback list is ranked at
the end of the default chain; canonical matches a table id at a '-'
boundary only; logCall/noteMain cannot unroute a step; route-tool failure
text no longer claims nothing was routed.
Repo side: mods suite probes the 'claude plugin test' usage line, doctor
bounds plugin list to 60 s, update-all skips @skills-dir mods.
Kit 431/431, full make test green.
The text regex becomes a prefilter. The command is split into simple
commands by an awk tokenizer (quotes, escapes, ; && || | ( ) backticks,
heredoc bodies dropped) and a push is only a simple command whose argv[0]
is git (or */git) with push or send-pack as its first non-option word.
grep "git push", git log -S, git config --get push.default, git stash
push, heredocs and commit messages quoting a push are no longer denied.
bash|sh|zsh -c scripts are re-checked (depth 3); wrappers (sudo, env,
eval, xargs, timeout, git subtree...), assignments whose value reads as
a push, a missing awk or > 2000 simple commands keep the text verdict.
Prefilter also matches "git" push (quote characters stripped).
Suite 98 -> 124 checks.
Plain composer prompts with no route in force get a turn-scoped effort
from $.model.classify (design/analysis/coding/bookkeeping/chat → phase
effort, effort only, never the model). Bounded by a 3 s clock race, a
user interrupt neither counts nor writes, three failures in a row pause
it for cooldownMinutes (one toast, status marker, cleared by /route
reload). No dialog, no routing.json write on a classified route. New
Config key `classify` (default on, pickSwitch), `/route classify on|off`
session toggle, `/route show` line and argumentHint. An explicit user
/effort beats the guess (engineBase check).
Docs: README classifier paragraph, USAGE row + sentence, CHANGELOG,
effort-shift.md. Kit suite 428 tests.
verbose now logs one line per real change, built from the decision
itself: main 'fable/high → fable/xhigh (plan: skill /ship-feature)' once
per turn per transition, a hand-off line per agent dispatch deduped per
(type, target) 'main fable/high → agent verifier sonnet/xhigh (row verify,
row)', a later agent effort move, and an answered-by anomaly for agents.
The four stream lines (step, answered by, spawn, route JSON, skill path)
are gone; the host prefixes the plugin name, so the new lines carry none.
Lines are built inside safely before next (a log failure never unroutes a
step); names are cleaned (≤ 40 code points). Residuals: failure texts go to
the log with a generic answer (forget, ask), file fragments cleaned at
render, floorFile name allowlisted, __proto__ refused in restoreOf, the
changed scan limited to rows, dialog Change offers only shipped phases,
a post-answer write failure keeps the key asked. Kit suite 284 → 358.
Contract .claude/tasks/contracts/2026-10-11-model-router-w4a-logs-residuals-1637.md,
plan r3: 3 lenses (BLOCKER: agent model moves are decided at spawn) + 1
confirmation, feater + 4 rounds, GATE 0 MET, verifier at the cap on
coverage (user-accepted), security PASS + 2 MEDIUM fixed.
Clears first-use decisions from the tracked routing.json through the
existing writer: a name is forgotten in every table (confirmed, changed
with the row restored to its recorded shipped phase under guards, project
exceptions pruned) and asked again; all and projects ask a confirmation in
the engine dialog (Cancel first) and hold the single-dialog slot; nothing
is written when there is nothing to forget; the answer names what was
restored and the frontmatter floor to realign when one was aligned; the
route tool has no forget path. Docs name the new writer. Kit suite 232 → 284.
Contract .claude/tasks/contracts/2026-10-11-model-router-w3c-forget-1457.md,
plan r3: 3 lenses + 1 confirmation, feater + 3 rounds (one real defect),
GATE 0 MET, verifier at the cap on coverage (user-accepted), security PASS.
The dialog now explains what it asks about: the skill's description (from
its SKILL.md frontmatter, five YAML forms, first sentence, cleaned), the
agent's description (from agent.offer), the phase's new 'about' line in
routing.json, and the real model id and effort the next step runs on.
Options Later / Keep / Change; Change asks the model (fable, opus, sonnet,
haiku with their tier role), then the effort among those the phases of
that model offer, then the scope; the pair maps to an existing phase (rows
stay phase names; the row's current phase wins a tie; same phase = Keep).
A main-loop phase (T3) is Later / Keep only. A main-row change toasts the
real decision and the /route switch hint when the pick is a downgrade.
Descriptions pass a hardened read (name allowlist, stat kind, size cap)
and clean(). Kit suite 190 → 232; W3-A dialog tests migrated.
Contract .claude/tasks/contracts/2026-10-11-model-router-w3b-dialog-1240.md,
plan r3: 3 lenses (2 BLOCKERs: inline rows, phase edits) + 1 confirmation,
feater + 2 rounds, GATE 0 MET, verifier CONFORME (3rd pass), security PASS.
routing.json (tracked, reached through the plugin directory) is now the
single source of the phase table and of every skill/agent row, plus the
decisions: confirmed rows/phases, changed rows (from/to) and projects
exceptions keyed by a normalized git remote (credentials never stored, no
machine paths). First use of a rowed typed skill, a rowed agent spawn or a
main-loop phase opens the engine's dialog (Later / Keep / two alternative
phases; Other = a phase name); a change asks Everywhere or This project
only. One dialog at a time, never in headless, never inside an agent,
never written by the model: only a dialog answer or /route ask writes,
serialized, size-capped, never creating the file. Layers: routing.json <
~/.claude/model-router.json; the project tree is never read. /route
pending, /route ask on|off. Census reads rows and phases from the file and
tolerates a user-changed row (WARN). Kit suite 86 → 190 tests.
Contract .claude/tasks/contracts/2026-10-10-model-router-w3a-confirm-1201.md,
plan r4: 3 lenses + 1 confirmation, feater + 4 rounds, GATE 0 MET,
verifier CONFORME then re-verify after security, security BLOCK(1) fixed
then PASS. Live: T2 dialogs answered by the user from the hot-loaded mod.
The 15 Skill(effort-*) citers now call mcp__model-router__route per phase
(orchestrate at a dispatch span, reflect/plan for the skill's own level,
apply at the bookkeeping tail, escalate at the verify-secure caps); built-in
judgment dispatches carry an explicit effort= param. lib/effort-shift.md is
the route doctrine, lib/model-gate.md the mod rule (route answer = witness,
/route on as remedy). Deleted: skills/effort-*, lib/effort-pins.txt/.sh,
lib/model-check.sh, their tests, the installers' re-apply blocks. The mod
drops its Skill(effort-*) bridge. The tracked model:/effort: frontmatter
stays as the off-state floor, census-locked equal to the rows
(lib/tests/effort-routing.test.sh rewritten, 140 checks; analyzer → xhigh).
Contract .claude/tasks/contracts/2026-10-10-model-router-w2b-1045.md, plan
r4 § W2-B: GATE 0 MET, verifier ECARTS(7) then CONFORME 10/10, security
PASS, full make test green (design-tool-gate env red only).
Rows by role replace the pins as the live source (frontmatter stays as the
off-state floor): phases write=work/high and apply=work/low, 56 skill rows,
21 agent rows + Explore/Plan. Agents get the row's model at spawn (within
the tier, upward only, explicit params win, project-defined agents skipped
via agent.offer) and its effort per step. A typed slash of a rowed skill
routes main through a name-bound marker (composer|sdk|bridge, pending slot
mid-turn) or the idle fallback; a best-tier row lives in a runMain slot
that survives turn end and route calls. An unrowed skill leaves the route.
Typed /effort-* floor code removed (bridge kept until W2-B). The route
answer always names the id. Override rows accept null. Kit suite 58 → 88.
Contract .claude/tasks/contracts/2026-10-09-model-router-w2a-1546.md, plan
r4 .claude/tasks/plans/2026-10-09-model-router-w2-1546.md: 3 lenses + 2
confirmations, feater + 4 rounds, GATE 0 MET, verifier 3x ECARTS on test
coverage only (user-accepted at the cap), security PASS.
A full make test printed only the == headers and an aggregate exit code,
so finding the red suite meant re-running every suite one by one (the
pre-merge check of 2026-10-09 took 7.5 min for that reason). The loop now
prints FAIL <suite> as it happens and ends with 'all suites green' or
'<n> suite(s) red: <names>'; the exit code is unchanged.